CircuitSeer: RTL Post-PnR Delay Prediction via Coupling Functional and Structural Representation
Register transfer level (RTL) optimization is a critical design phase that ensures timing closure and performance. Although machine learning (ML) has been utilized to quickly predict post-synthesis delay metrics, estimating post-place and route (PnR) delay remains a significant challenge. This is due to the distinct functionality-preserving characteristics of logic synthesis and the structure-dependent aspect of physical design. Furthermore, Logic Synthesis heavily restructures the netlist, resulting in substantial structural disparities that hinder capturing the post-synthesis netlist structure.
Authors
- Sandip Kumar Samanta (ORCID: https://orcid.org/0009-0004-2017-5155)
- Hao Zheng (ORCID: https://orcid.org/0000-0003-4391-2774)
- Sanjay Gandham (ORCID: https://orcid.org/0000-0002-5819-1773)
- Mingjie Lin (ORCID: https://orcid.org/0000-0002-3225-4406)
- Joe Walston
- Lingxiang Yin (ORCID: https://orcid.org/0009-0005-9279-9220)
- Stelios Diamantidis
Institutions
- University of Central Florida (US)
- Synopsys (United States) (US)
Publication Details
- Published
- 2024-10-27
- DOI
- https://doi.org/10.1145/3676536.3676668
- Primary Topic
- VLSI and Analog Circuit Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00